Tacotron-2:

Tensorflow implementation of DeepMind's Tacotron-2. A deep neural network architecture described in this paper: Natural TTS synthesis by conditioning Wavenet on MEL spectogram predictions

This Repository contains additional improvements and attempts over the paper, we thus propose paper_hparams.py file which holds the exact hyperparameters to reproduce the paper results without any additional extras.

Suggested hparams.py file which is default in use, contains the hyperparameters with extras that proved to provide better results in most cases. Feel free to toy with the parameters as needed.

DIFFERENCES WILL BE HIGHLIGHTED IN DOCUMENTATION SHORTLY.

Repository Structure:

Tacotron-2
├── datasets
├── en_UK		(0)
│   └── by_book
│       └── female
├── en_US		(0)
│   └── by_book
│       ├── female
│       └── male
├── LJSpeech-1.1	(0)
│   └── wavs
├── logs-Tacotron	(2)
│   ├── eval_-dir
│   │ 	├── plots
│ 	│ 	└── wavs
│   ├── mel-spectrograms
│   ├── plots
│   ├── taco_pretrained
│   ├── metas
│   └── wavs
├── logs-Wavenet	(4)
│   ├── eval-dir
│   │ 	├── plots
│ 	│ 	└── wavs
│   ├── plots
│   ├── wave_pretrained
│   ├── metas
│   └── wavs
├── logs-Tacotron-2	( * )
│   ├── eval-dir
│   │ 	├── plots
│ 	│ 	└── wavs
│   ├── plots
│   ├── taco_pretrained
│   ├── wave_pretrained
│   ├── metas
│   └── wavs
├── papers
├── tacotron
│   ├── models
│   └── utils
├── tacotron_output	(3)
│   ├── eval
│   ├── gta
│   ├── logs-eval
│   │   ├── plots
│   │   └── wavs
│   └── natural
├── wavenet_output	(5)
│   ├── plots
│   └── wavs
├── training_data	(1)
│   ├── audio
│   ├── linear
│	└── mels
└── wavenet_vocoder
	└── models

The previous tree shows the current state of the repository (separate training, one step at a time).

• Step (0): Get your dataset, here I have set the examples of Ljspeech, en_US and en_UK (from M-AILABS).

• Step (1): Preprocess your data. This will give you the training_data folder.

• Step (2): Train your Tacotron model. Yields the logs-Tacotron folder.

• Step (3): Synthesize/Evaluate the Tacotron model. Gives the tacotron_output folder.

• Step (4): Train your Wavenet model. Yield the logs-Wavenet folder.

• Step (5): Synthesize audio using the Wavenet model. Gives the wavenet_output folder.

• Note: Steps 2, 3, and 4 can be made with a simple run for both Tacotron and WaveNet (Tacotron-2, step ( * )).

Note:

• Our preprocessing only supports Ljspeech and Ljspeech-like datasets (M-AILABS speech data)! If running on datasets stored differently, you will probably need to make your own preprocessing script.
• In the previous tree, files were not represented and max depth was set to 3 for simplicity.
• If you run training of both models at the same time, repository structure will be different.

Pretrained model and Samples:

Pre-trained models and audio samples will be added at a later date. You can however check some primary insights of the model performance (at early stages of training) here. THIS IS VERY OUTDATED, I WILL UPDATE THIS SOON

Model Architecture:

The model described by the authors can be divided in two parts:

• Spectrogram prediction network
• Wavenet vocoder

To have an in-depth exploration of the model architecture, training procedure and preprocessing logic, refer to our wiki

Current state:

To have an overview of our advance on this project, please refer to this discussion

since the two parts of the global model are trained separately, we can start by training the feature prediction model to use his predictions later during the